© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6262
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are generally positive or descriptive in nature

    oai_token-act-pair · gemini-2.0-flash

    General statements/opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.98
     touches
    -0.94
     sacrifices
    -0.91
     connotations
    -0.90
     remarks
    -0.89
     tones
    -0.88
     privileges
    -0.87
     memories
    -0.87
     metaphors
    -0.87
     motions
    -0.86
    POSITIVE LOGITS
     navires
    0.59
     vaisseaux
    0.57
     églises
    0.57
     pères
    0.52
     lèvres
    0.49
     épaules
    0.48
     example
    0.47
     émissions
    0.46
     condition
    0.46
     list
    0.45
    Activations Density 13.339%

    No Known Activations